Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4575 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 6.1809. Min Range: -6.1809

Max Act: 6.1809. Min Act: -0.0000

Data Index: 1564292 (Python Code)

Max Activating Token Index: 968

Text #1

Max Range: 6.1809. Min Range: -6.1809

Max Act: 5.4260. Min Act: -0.0000

Data Index: 1603071 (Python Code)

Max Activating Token Index: 301

Text #2

Max Range: 6.1809. Min Range: -6.1809

Max Act: 5.8225. Min Act: -0.0000

Data Index: 1505346 (Python Code)

Max Activating Token Index: 961

Text #3

Max Range: 6.1809. Min Range: -6.1809

Max Act: 5.8103. Min Act: -0.0000

Data Index: 1590528 (Python Code)

Max Activating Token Index: 50

Text #4

Max Range: 6.1809. Min Range: -6.1809

Max Act: 5.7356. Min Act: -0.0000

Data Index: 1650603 (Python Code)

Max Activating Token Index: 643

Text #5

Max Range: 6.1809. Min Range: -6.1809

Max Act: 5.7081. Min Act: -0.0000

Data Index: 1629403 (Python Code)

Max Activating Token Index: 840

Text #6

Max Range: 6.1809. Min Range: -6.1809

Max Act: 5.2160. Min Act: -0.0000

Data Index: 1498352 (Python Code)

Max Activating Token Index: 870

Text #7

Max Range: 6.1809. Min Range: -6.1809

Max Act: 5.3446. Min Act: -0.0000

Data Index: 1590533 (Python Code)

Max Activating Token Index: 711

Text #8

Max Range: 6.1809. Min Range: -6.1809

Max Act: 5.3267. Min Act: -0.0000

Data Index: 1401945 (Python Code)

Max Activating Token Index: 716

Text #9

Max Range: 6.1809. Min Range: -6.1809

Max Act: 5.4717. Min Act: -0.0000

Data Index: 1622693 (Python Code)

Max Activating Token Index: 26

Text #10

Max Range: 6.1809. Min Range: -6.1809

Max Act: 5.4781. Min Act: -0.0000

Data Index: 1543058 (Python Code)

Max Activating Token Index: 848

Text #11

Max Range: 6.1809. Min Range: -6.1809

Max Act: 5.4612. Min Act: -0.0000

Data Index: 1569493 (Python Code)

Max Activating Token Index: 73

Text #12

Max Range: 6.1809. Min Range: -6.1809

Max Act: 5.0325. Min Act: -0.0000

Data Index: 1616139 (Python Code)

Max Activating Token Index: 60

Text #13

Max Range: 6.1809. Min Range: -6.1809

Max Act: 5.2296. Min Act: -0.0000

Data Index: 1363440 (Python Code)

Max Activating Token Index: 199

Text #14

Max Range: 6.1809. Min Range: -6.1809

Max Act: 5.1842. Min Act: -0.0000

Data Index: 1463322 (Python Code)

Max Activating Token Index: 1000

Text #15

Max Range: 6.1809. Min Range: -6.1809

Max Act: 5.4034. Min Act: -0.0000

Data Index: 1428104 (Python Code)

Max Activating Token Index: 32

Text #16

Max Range: 6.1809. Min Range: -6.1809

Max Act: 5.1960. Min Act: -0.0000

Data Index: 1528098 (Python Code)

Max Activating Token Index: 112

Text #17

Max Range: 6.1809. Min Range: -6.1809

Max Act: 5.5324. Min Act: -0.0000

Data Index: 1492646 (Python Code)

Max Activating Token Index: 206

Text #18

Max Range: 6.1809. Min Range: -6.1809

Max Act: 5.5670. Min Act: -0.0000

Data Index: 1432821 (Python Code)

Max Activating Token Index: 279

Text #19

Max Range: 6.1809. Min Range: -6.1809

Max Act: 4.9783. Min Act: -0.0000

Data Index: 1401595 (Python Code)

Max Activating Token Index: 450